Novel dry bulk port multi-scene simulation method based on large language model

Abstract

The invention discloses a novel dry bulk cargo port multi-scene simulation method based on a large language model, belongs to the technical field of port production and operation, and realizes the expansion of training samples by using the general knowledge of the large language model; based on an Adam optimizer, training the initial model by adopting the training set, and verifying the initial model by adopting the verification set; evaluating a multi-scene simulation result under the guidance of the model based on a test result of the test set, and performing iterative expansion training by utilizing a prompt learning mechanism in combination with multi-scene data to obtain a trained large language model; extracting key semantics of scene features through the trained large language model according to a current operation scene of a port; performing simulation resource configuration reasoning on the extracted key semantics; a novel dry bulk port simulation model in a corresponding scene is constructed by adopting AnyLogic simulation, and a big language model training corpus and a training set are updated according to a simulation preview result and port actual operation data. According to the invention, the production operation decision can be optimized.

Description

Technical Field

[0001] The present invention belongs to the technical field of port production and operation, and more specifically, relates to a novel dry bulk port multi-scenario simulation method based on a large language model. Background Art

[0002] With the rapid growth of global trade, dry bulk ports, as important transportation hubs and trading nodes for global food and industrial raw materials, have a direct impact on the stability and efficiency of the global supply chain due to their operational efficiency and management level. However, the traditional management methods of dry bulk ports are limited by manual experience and are difficult to cope with the increasingly complex and changing operating environment and operational requirements. Therefore, promoting intelligent port management has become the key to port development.

[0003] The new type of "bulk-to-container" dry bulk port uses containers to achieve bulk storage and transportation, and constructs horizontal transportation and loading and unloading facilities for bulk containers based on the air-rail collection and distribution system. It can effectively solve the problems of low port circulation and transportation efficiency and heavy port pollution in existing bulk ports, and has good application prospects and market potential.

[0004] As a new technology in the field of natural language processing, the large language model has deep learning capabilities based on massive text data training, which enables the model to deeply understand the meaning of text and handle various complex natural language tasks. Applying the large language model to the multi-scenario simulation of dry bulk ports can effectively solve the production and operation problems of dry bulk ports, such as limited port historical data and complex configuration of port multi-scenario simulation models, and provide new ideas for dry bulk port management.

[0005] By collecting port operation-related data, such as equipment performance, operation time, material attributes, etc., a large language model is trained to perform port multi-scenario simulation resource configuration reasoning. Based on this, a virtual port environment is built to simulate real port operation scenarios and realize multi-scenario simulation operation. This simulation method provides ports with multi-scenario simulation preview results, thereby realizing intelligent decision support for dry bulk ports, such as equipment scheduling, operation plan optimization, etc., thereby improving port operation efficiency, reducing operating costs, and ensuring operation safety.

[0006] In summary, the multi-scenario simulation method of new dry bulk ports based on the large language model can effectively promote the improvement of the intelligent management level of new dry bulk ports and the sustainable development of ports with its powerful natural language processing capabilities and intelligent decision-making support.

[0007] Traditional dry bulk ports rely on manual experience for production and operation management, which makes it difficult to respond to diverse production environments and decision-making needs in a timely manner. The multi-scenario simulation method for new dry bulk ports based on large language models can be applied to new "bulk-to-container" dry bulk ports, promoting the improvement of the intelligent management level of new dry bulk ports and the sustainable development of ports.

[0008] (1) Data limitations and difficulty in model configuration

[0009] In complex scenarios, traditional dry bulk port operation data accumulation is limited, and it is difficult to ensure the integrity and accuracy of data records, which limits the effectiveness of decision-making models based on data analysis. Through the powerful natural language processing capabilities of the large language model, data limitations can be overcome, and more sophisticated and comprehensive model configurations can be achieved, improving simulation accuracy and generalization capabilities.

[0010] (2) Difficulty in optimizing operational efficiency and resources

[0011] When dealing with emergencies, manual scheduling and planning cannot be adjusted dynamically, resulting in low operating efficiency. At the same time, there is a lack of decision support systems based on big data analysis, which leads to a strong subjectivity in the decision-making process and weak risk control capabilities. By collecting relevant data on port operations, such as equipment performance, operation time, material attributes, etc., a large language model is trained to perform multi-scenario simulation resource configuration reasoning for ports. Based on this, AnyLogic is used to build a virtual port environment, simulate real port operation scenarios, and realize multi-scenario simulation operations. This simulation method provides ports with multi-scenario simulation preview results, thereby realizing intelligent decision support for dry bulk ports, such as equipment scheduling, operation plan optimization, etc., improving port operation efficiency, reducing operating costs, and ensuring operation safety. Summary of the invention

[0012] In view of the above defects or improvement needs of the prior art, the present invention proposes a new multi-scenario simulation method for dry bulk ports based on a large language model to solve the production and operation management problems of the new "bulk-to-container" dry bulk ports.

[0013] To achieve the above object, the present invention provides a novel dry bulk port multi-scenario simulation method based on a large language model, comprising:

[0014] According to the simulation preview requirements of the new type of bulk-to-container dry bulk port, combined with historical simulation data, port production scenarios and simulation data under multiple operation scenarios are collected as training samples;

[0015] The general knowledge of the large language model is used to expand the training samples, and the expanded training samples are divided into training sets, test sets, and validation sets.

[0016] Based on the Adam optimizer, the initial large language model is trained using the training set, and the initial large language model is verified using the validation set;

[0017] Based on the test results of the test set, the multi-scenario simulation results under the guidance of the large language model are evaluated, and the prompted learning mechanism is used to perform iterative expansion training in combination with multi-scenario data to obtain the trained large language model;

[0018] According to the current operation scene of the port, the scene feature corpus is input, and the key semantics of the scene features are extracted through the trained large language model;

[0019] Use the trained large language model to perform simulation resource configuration reasoning based on the extracted key semantics, thereby obtaining the simulation resource configuration for the current job scenario;

[0020] Based on the simulation resource configuration provided by the trained large language model, AnyLogic simulation software was used to build a new dry bulk port simulation model for the corresponding scenario, providing simulation preview results for the port.

[0021] Update the large language model training corpus and training set based on simulation rehearsal results and actual port operation data.

[0022] In some optional implementation schemes, new dry bulk port operation scenarios include:

[0023] Loading system: It consists of forklifts and yard cranes and is responsible for container loading operations;

[0024] Unloading system: It consists of a car tipper and a belt conveyor, responsible for unloading bulk cargo from trains;

[0025] Belt unit: It consists of multiple belt lines and is responsible for bulk cargo transportation within the yard;

[0026] Stacking system: It consists of a stacker and a belt conveyor, responsible for stacking the unloaded bulk cargo as required;

[0027] Packing system: It consists of a belt conveyor and a packing crane and is responsible for the bulk cargo filling operation of the container;

[0028] Skyrail collection and distribution system: It consists of six major systems: track, train, transportation control, power supply and communication, transfer and information dispatching, and is responsible for the collection and distribution and loading and unloading of containers in the yard;

[0029] Loading system: It consists of a quay crane and a belt conveyor, responsible for container loading operations;

[0030] Ship unloading system: It consists of a ship unloader and a belt conveyor and is responsible for bulk cargo unloading operations.

[0031] In some optional implementation schemes, the new dry bulk port multi-scenario simulation targets 6 sub-operation scenarios and their mixed operation scenarios:

[0032] Train loading operation scenario: filling bulk cargo into containers according to the needs of arriving trains, and then loading containers onto trains;

[0033] Train unloading operation scene: the operation scene of unloading bulk cargo loaded on the train at the port to the yard;

[0034] Car loading operation scenario: filling bulk cargo into containers according to the demand of cars arriving at the port, and then loading the containers into cars;

[0035] Truck unloading operation scene: the operation scene of unloading bulk cargo in the container loaded by the truck at the port to the yard;

[0036] Ship loading operation scenario: filling bulk cargo into containers according to the needs of arriving ships, and then loading the containers onto ships;

[0037] Ship unloading operation scenario: the operation scenario of unloading bulk cargo from a ship at port to the storage yard.

[0038] In some optional implementation schemes, the port production scenarios and simulation data under multiple operation scenarios collected according to the dry bulk port simulation preview requirements and combined with historical simulation data as training samples include:

[0039] Resource allocation data include: port structure information, including terminal layout and division, berth quantity and type, sea freight lines, railway freight lines, and automobile freight lines; equipment information includes: the number, type, and performance parameters of loading and unloading equipment, belt conveyors, and horizontal transportation equipment; personnel allocation information includes: the number, skill level, and working hours of operators, managers, and maintenance personnel; storage capacity information includes: the storage capacity of the yard;

[0040] The simulation configuration data includes: time parameters include: total simulation running time, time step; input / output data include: freight volume, cargo type, arrival and departure time, loading and unloading time; rule strategies include: scheduling rules, job priority, resource allocation strategy; model parameters include: queue length, storage area and height;

[0041] The simulation performance data includes: throughput includes: the amount of cargo handled by the port within the preset time; operation time includes: vehicle and ship waiting time, loading and unloading time, transportation time; resource utilization includes: equipment utilization, staffing utilization; congestion includes: vehicle / ship queue length, warehouse inventory.

[0042] In some optional implementation schemes, the expansion of training samples using the general knowledge of the large language model includes:

[0043] Using the text generation capability of the large language model, a descriptive text is generated based on the defined operation scenarios and simulation data to cover the port operation conditions and simulation data under various operation weather conditions, operation states and operation time periods;

[0044] According to the historical simulation data format, the descriptive text is converted into structured data suitable for training the simulation model. Through manual review and simulation model testing, it is ensured that the generated samples conform to the physical laws and port business logic.

[0045] Based on the preliminary simulation results and feedback, the input prompts, generation parameters and data conversion synthesis rules of the large language model are continuously adjusted.

[0046] In some optional implementation schemes, the training of the initial large language model using the training set and the verification of the initial large language model using the verification set include:

[0047] Divide the training set into multiple subsets according to the set batch size;

[0048] Randomly extract a batch of data from the training set as the input data and corresponding target value of the current iteration;

[0049] Input the current batch of data into the initial large language model and calculate the predicted value through forward propagation;

[0050] Given a target text sequence Y(y1,y2,...y T ), calculate the loss function value based on the predicted value and the true target value: Among them, T is the length of the target text sequence, and the probability distribution predicted by the large language model at each step t is y t is the true value of the target sequence at time t;

[0051] Depend on Calculate the gradient of the loss function with respect to the parameters of the large language model, where is the gradient of the average loss function of the entire sequence with respect to the parameters. For a given target text sequence Y and the probability distribution predicted by the model, θ is the model parameter;

[0052] The update rule of the Adam optimizer is used to update the large language model parameters, where the first-order moment estimate is updated as Update the second-order moment estimate to The deviation is corrected to Update the parameters to β1 and β2 are hyperparameters, α is the learning rate, t is the current number of iterations, ∈ is a very small positive number, and m t is the first-order exponentially weighted moving average of the gradient, v t is the second-order exponentially weighted moving average of the squared gradient, is the bias-corrected first-order moment, is the bias-corrected second-order moment, θ t+1 To update the parameters;

[0053] After all batches have been iterated, the model is validated using the validation set. If the validation result fails, the model is returned to the step of dividing the training set into multiple subsets according to the set batch size until the validation result passes.

[0054] In some optional implementation schemes, the test results based on the test set are used to evaluate the multi-scenario simulation results under the guidance of the large language model, and the prompt learning mechanism is used to perform iterative expansion training in combination with multi-scenario data to obtain the trained large language model, including:

[0055] Use the test set to evaluate the performance of the initial large language model, including model accuracy, stability, and generalization ability;

[0056] Identify model deficiencies based on evaluation results and guide the model’s behavior in corresponding scenarios by defining new prompt functions or modifying existing prompts;

[0057] By continuously collecting multi-scenario data, adjusting prompt templates and training strategies, the large language model is trained multiple times.

[0058] In some optional implementation schemes, the large language model is trained multiple times by continuously collecting multi-scenario data, adjusting prompt templates and training strategies, including:

[0059] As iterative training progresses, new multi-simulation scenario data is continuously collected, preprocessed, and labeled;

[0060] Use the designed prompt template to convert the raw data into the form of prompt input;

[0061] Input the prompt input and the corresponding label into the pre-trained large language model for training;

[0062] Based on the difference between the output of the large language model and the true label, the loss function is calculated and the model parameters are updated through back propagation;

[0063] After each iteration, use the validation set or test set to evaluate the performance of the large language model.

[0064] Adjust the design of the prompt template based on the evaluation results, and adjust the training strategy based on the performance of the large language model during training;

[0065] Continue to iterate, constantly collect new data, adjust prompts and training strategies, and iterate training until performance evaluation passes.

[0066] In some optional implementation schemes, the inputting of scene feature corpus according to the current operation scene of the port and extracting key semantics of the scene features through the trained large language model include:

[0067] Select text data related to the current port operation scenario, remove invalid information from the text data, and convert unstructured data into a structured format;

[0068] The large language model uses advanced semantic analysis to identify and distinguish key words, phrases and conceptual entities in the text, and directly maps them to key parameters and operating modes of port operations;

[0069] Mining the meaning of keywords and phrases in specific scenarios, using contextual information to analyze their functions and relationships, and extracting key semantic information of simulation configurations.

[0070] In some optional implementation schemes, the use of the trained large language model to perform simulation resource configuration reasoning on the extracted key semantics, thereby obtaining the simulation resource configuration in the current job scenario, includes:

[0071] Based on key semantic information, the trained large language model is used to perform simulation resource configuration reasoning. By analyzing the current operation scenario and building the simulation scenario, a reasonable resource configuration plan is inferred, including the quantity allocation of resources such as loading and unloading equipment, transport vehicles, and storage space, operation path planning, and shift scheduling.

[0072] In some optional implementation schemes, the simulation resource configuration provided by the trained large language model is used to construct a new dry bulk port simulation model in the corresponding scenario using AnyLogic simulation software to provide simulation preview results for the port, including:

[0073] Using the simulation resource configuration data provided by the big language model as input, AnyLogic simulation software was used to build an operational system model of a new dry bulk port, including port infrastructure layout, equipment configuration, and operational processes such as ship arrival, cargo loading and unloading, storage, and transportation.

[0074] Run the simulation model to observe the operation of the port in actual operation, collect simulation preview results of operation time, operation efficiency, equipment utilization, and terminal throughput, so as to make production and operation decisions for the port.

[0075] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0076] (1) The present invention uses the Adam optimizer to train the initial model and uses a validation set to verify the model, ensuring the training effect and generalization ability of the model. At the same time, it combines the prompt learning mechanism to perform iterative expansion training, so that the multi-scenario simulation performance under the guidance of the large language model is further improved.

[0077] (2) The present invention effectively solves the problem of port simulation data scale limitations by combining historical simulation data and general knowledge of large language models, realizes the expansion of training samples, and significantly improves the richness and accuracy of simulation data. At the same time, the present invention extracts the key semantics of port operation scenarios through large language models, and performs simulation resource configuration reasoning based on these key semantics, thereby realizing an intelligent and automated resource configuration process. It improves the efficiency and accuracy of resource allocation, reduces the need for human intervention, and improves the level of intelligence of port production operations.

[0078] (3) Based on the simulation resource configuration provided by the large language model, the present invention uses AnyLogic simulation software to build a new dry bulk port simulation model under the corresponding scenario, providing simulation preview results for the port. It accurately simulates the actual port operation situation, optimizes production and operation decisions, reduces unnecessary resource waste and cost expenditure, and improves the overall operation efficiency of the port. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a flow chart of a novel multi-scenario simulation method for dry bulk cargo ports based on a large language model provided by an embodiment of the present invention;

[0080] Figure 2 It is a schematic diagram of a new type of dry bulk cargo port operation scenario mainly applied by a new type of dry bulk cargo port multi-scenario simulation method provided by an embodiment of the present invention;

[0081] Figure 3 This is a schematic diagram of initial model training and verification provided by an embodiment of the present invention;

[0082] Figure 4 This is a schematic diagram of an operation system model of a new type of dry bulk port constructed using AnyLogic simulation software, provided by an embodiment of the present invention;

[0083] Figure 5 It is a schematic diagram of an iterative training process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0084] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0085] The technical solution of the present invention is: a new multi-scenario simulation method for dry bulk ports based on a large language model, such as Figure 1 As shown, the specific steps include:

[0086] S1. Aiming at the multi-scenario simulation problem of the new type of dry bulk port, according to the simulation preview requirements of dry bulk ports, combined with historical simulation data, the port production scenarios and simulation data under multiple operation scenarios are collected, including resource configuration data, simulation configuration data and simulation performance data;

[0087] S2. Considering the scale limitation of the port multi-scenario simulation data, the general knowledge of the large language model is used to expand the training samples, and the expanded training samples are divided into training set, test set and validation set;

[0088] S3. Based on the Adam optimizer, the initial model is trained using the training set and verified using the verification set;

[0089] S4. Evaluate the multi-scenario simulation results under the guidance of the large language model based on the test results of the test set, and use the prompt learning mechanism and multi-scenario data to perform iterative expansion training to further improve the multi-scenario simulation performance under the guidance of the large language model;

[0090] S5. According to the current operation scene of the port, input the scene feature corpus, and extract the key semantics of the scene features through the trained large language model;

[0091] S6. Use the trained large language model to perform simulation resource configuration reasoning on the extracted key semantics, thereby obtaining the simulation resource configuration in the current job scenario;

[0092] S7. Based on the simulation resource configuration provided by the large language model, AnyLogic simulation software was used to build a new dry bulk port simulation model for the corresponding scenario, providing simulation preview results for the port to support the decision-making of port production operations;

[0093] S8. Update the large language model training corpus and training set based on the simulation results and actual port operation data to conduct a new round of simulation rehearsals.

[0094] In the above example, if Figure 2 As shown, the new dry bulk cargo port multi-scenario simulation method is mainly applied to the new dry bulk cargo port operation scenario, wherein the new dry bulk cargo port operation scenario includes the following main components:

[0095] Loading system: It consists of forklifts and yard cranes and is responsible for container loading operations;

[0096] Unloading system: It consists of a car tipper and a belt conveyor, responsible for unloading bulk cargo from trains;

[0097] Belt unit: It consists of multiple belt lines and is responsible for bulk cargo transportation within the yard;

[0098] Stacking system: It consists of a stacker and a belt conveyor, responsible for stacking the unloaded bulk cargo as required;

[0099] Packing system: It consists of a belt conveyor and a packing crane and is responsible for the bulk cargo filling operation of the container;

[0100] Skyrail collection and distribution system: It consists of six major systems: track, train, transportation control, power supply and communication, transfer and information dispatching, and is responsible for the collection and distribution and loading and unloading of containers in the yard;

[0101] Loading system: It consists of a quay crane and a belt conveyor, responsible for container loading operations;

[0102] Ship unloading system: It consists of a ship unloader and a belt conveyor and is responsible for bulk cargo unloading operations.

[0103] In the above example, the multi-scenario simulation of the new dry bulk port mainly targets 6 sub-operation scenarios and their mixed operation scenarios:

[0104] Train loading operation scenario: filling bulk cargo into containers according to the needs of arriving trains, and then loading containers onto trains;

[0105] Train unloading operation scene: the operation scene of unloading bulk cargo loaded on the train at the port to the yard;

[0106] Car loading operation scenario: filling bulk cargo into containers according to the demand of cars arriving at the port, and then loading the containers into cars;

[0107] Truck unloading operation scene: the operation scene of unloading bulk cargo in the container loaded by the truck at the port to the yard;

[0108] Ship loading operation scenario: filling bulk cargo into containers according to the needs of arriving ships, and then loading the containers onto ships;

[0109] Ship unloading operation scenario: the operation scenario of unloading bulk cargo from a ship at port to the storage yard.

[0110] In the above example, in step S1, according to the dry bulk port simulation preview requirements, combined with historical simulation data, the port production scenarios and simulation data under multiple operation scenarios collected mainly include:

[0111] Resource allocation data: port structure information, including terminal layout and zoning, berth quantity and type, sea freight lines, railway freight lines, automobile freight lines, etc.; equipment information, including the quantity, type, and performance parameters of loading and unloading equipment, belt conveyors, and horizontal transportation equipment; personnel configuration information, including the number, skill level, and working hours of operators, managers, and maintenance personnel; storage capacity information, including the storage capacity of the yard.

[0112] Simulation configuration data: time parameters, including the total simulation running time and time step; input / output data, including freight volume, cargo type, arrival and departure time, loading and unloading time; rule strategies, including scheduling rules, job priority, resource allocation strategy, etc.; model parameters, including queue length, storage area and height, etc.

[0113] Simulation performance data: throughput, the amount of cargo handled by the port in a certain period of time; operation time, including vehicle and ship waiting time, loading and unloading time, and transportation time; resource utilization, including equipment utilization, staffing utilization, etc.; congestion, including vehicle / ship queue length, warehouse inventory, etc.

[0114] In the above example, in step S2, the general knowledge of the large language model is used to expand the training samples and divide the expanded training samples; the training sample expansion process is as follows:

[0115] S21. Utilize the text generation capability of the large language model to generate a large amount of descriptive text based on the defined operation scenarios and simulation data to cover the port operation conditions and simulation data under various operation weather conditions, various operation states and various operation time periods.

[0116] S22. According to the historical simulation data format, the descriptive text is converted into structured data suitable for training the simulation model. Through manual review and simulation model testing, it is ensured that the generated samples conform to the physical laws and port business logic, and have practical value and credibility.

[0117] S23. Based on the preliminary simulation results and feedback, continuously adjust the input prompts, generation parameters, and data conversion and synthesis rules of the large language model to improve the quality and applicability of the expanded samples through multiple iterations.

[0118] In the above example, if Figure 3 As shown, in step S3, the steps of using the training set to train the initial model and using the verification set to verify the initial model are as follows:

[0119] S31. A training loop, dividing the training data set into multiple subsets according to a set batch size;

[0120] S32. Data sampling: randomly extract a batch of data from the training set as the input data and corresponding target value of the current iteration;

[0121] S33. Forward propagation: input the data of the current batch into the model and calculate the predicted value through forward propagation;

[0122] S34. Calculate the loss, given the target text sequence Y(y1,y2,...y T), calculate the loss function value based on the predicted value and the true target value;

[0123]

[0124] Where T is the sequence length, and the probability distribution predicted by the model at each step t is

[0125] S35. Back propagation, calculating the gradient of the loss function with respect to the model parameters;

[0126]

[0127] S36. Update parameters, use the update rule of the Adam optimizer to update the model parameters, including calculating the first-order moment estimate and the second-order moment estimate, correcting the deviation, and updating the model parameters accordingly.

[0128] Update first moment estimate

[0129] Update the second moment estimate

[0130] Bias Correction

[0131] Update Parameters

[0132] Among them, β1 and β2 are hyperparameters, α is the learning rate, t is the current number of iterations, and ∈ is a very small positive number.

[0133] S37. Validation set validation: after all batches are iterated, the model is validated using the validation set;

[0134] S38. Check the result. If the verification result fails, jump to step S31 and continue to execute until the verification result passes.

[0135] In the above example, in step S4, the multi-scenario simulation results under the guidance of the large language model are evaluated based on the test results of the test set, and the steps of iterative expansion training using the prompt learning mechanism are as follows:

[0136] S41. Test result evaluation: using the test set to perform performance evaluation on the initial model, including model accuracy, stability and generalization ability;

[0137] S42. Prompt learning mechanism, which identifies model deficiencies based on evaluation results and guides the model’s behavior in corresponding scenarios by defining new prompt functions or modifying existing prompts;

[0138] S43. Iterative training process, by continuously collecting multi-scenario data, adjusting prompt templates and training strategies, training the large language model multiple times to improve the multi-scenario simulation performance under the guidance of the large language model.

[0139] In the above example, in step S5, according to the current operation scene of the port, the scene feature corpus closely related to the operation is collected and preprocessed, and the trained large language model is used to perform in-depth analysis and semantic understanding on the corpus, and the steps of extracting key semantic information of the scene features from it are as follows:

[0140] S51. Collect scene feature corpus and select text data related to the current port operation scene, including detailed descriptions of cargo type, loading and unloading operations, equipment use, staffing, environmental conditions, etc.;

[0141] S52. Data preprocessing: removing invalid information from the corpus, ensuring data quality, and converting unstructured data into a structured format to facilitate model understanding;

[0142] S53. Semantic analysis: The model uses advanced semantic analysis to identify and distinguish key words, phrases and conceptual entities in the text, and directly maps them to key parameters and operation modes of port operations;

[0143] S54. Key information extraction: deeply explore the meaning of keywords and phrases in specific scenarios, use contextual information to analyze their functions and relationships, and extract key semantic information of simulation configuration.

[0144] In the above example, in step S6, based on the key semantic information, the trained large language model is used to perform simulation resource configuration reasoning. Through in-depth analysis of the current operation scene and construction of the simulation scene, a reasonable resource configuration plan is inferred, including the quantity allocation of resources such as loading and unloading equipment, transportation vehicles, and storage space, operation path planning, shift scheduling, etc.

[0145] In the above example, if Figure 4 As shown, in step S7, the simulation resource configuration data provided by the large language model is used as input, and the AnyLogic simulation software is used to build an operation system model of a new type of dry bulk port, including port infrastructure layout, equipment configuration, ship arrival, cargo loading and unloading, storage, transportation and other operation processes. The simulation model is simulated and run to observe the operation of the port in actual operations, and simulation preview results such as operation time, operation efficiency, equipment utilization, and terminal throughput are collected. Accurately make production and operation decisions for the port, such as optimizing resource allocation and adjusting operation processes, to maximize port operation efficiency.

[0146] In the above example, if Figure 5 As shown, the iterative training process steps are as follows:

[0147] S431. Collect and annotate data. As iterative training progresses, new multi-simulation scene data is continuously collected, preprocessed and annotated;

[0148] S432. Construct prompt input, use the designed prompt template to convert the original data into the form of prompt input;

[0149] S433. Model training, inputting the prompt input and the corresponding label into the pre-trained model for training;

[0150] S434. Update parameters, calculate the loss function according to the difference between the output of the model and the true label, and update the model parameters through back propagation;

[0151] S435. Evaluate model performance. After each iteration, use the validation set or test set to evaluate the performance of the model.

[0152] S436. Adjust prompts and training strategies. According to the evaluation results, adjust the design of prompt templates to better guide the model to focus on key information, and adjust the training strategies such as learning rate and batch size according to the performance of the model during training;

[0153] S437. Continue to iterate, repeat the above steps, continuously collect new data, adjust prompts and training strategies, and perform iterative training until the performance evaluation passes.

[0154] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, and two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0155] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A new multi-scenario simulation method for dry bulk ports based on a large language model, characterized in that: include: According to the simulation preview requirements of the new type of bulk-to-container dry bulk port, combined with historical simulation data, port production scenarios and simulation data under multiple operation scenarios are collected as training samples; The general knowledge of the large language model is used to expand the training samples, and the expanded training samples are divided into training sets, test sets, and validation sets. Based on the Adam optimizer, the initial large language model is trained using the training set, and the initial large language model is verified using the validation set; Based on the test results of the test set, the multi-scenario simulation results under the guidance of the large language model are evaluated, and the prompted learning mechanism is used to perform iterative expansion training combined with multi-scenario data to obtain the trained large language model; According to the current operation scene of the port, the scene feature corpus is input, and the key semantics of the scene features are extracted through the trained large language model; Use the trained large language model to perform simulation resource configuration reasoning based on the extracted key semantics, thereby obtaining the simulation resource configuration for the current job scenario; Based on the simulation resource configuration provided by the trained large language model, AnyLogic simulation software was used to build a new dry bulk port simulation model for the corresponding scenario, providing simulation preview results for the port. Update the large language model training corpus and training set based on simulation rehearsal results and actual port operation data.

2. The method according to claim 1, characterized in that New dry bulk port operation scenarios include: Loading system: It consists of forklifts and yard cranes and is responsible for container loading operations; Unloading system: It consists of a car tipper and a belt conveyor, responsible for unloading bulk cargo from trains; Belt unit: It consists of multiple belt lines and is responsible for bulk cargo transportation within the yard; Stacking system: It consists of a stacker and a belt conveyor, responsible for stacking the unloaded bulk cargo as required; Packing system: It consists of a belt conveyor and a packing crane and is responsible for the bulk cargo filling operation of the container; Skyrail collection and distribution system: It consists of six major systems: track, train, transportation control, power supply and communication, transfer and information dispatching, and is responsible for the collection and distribution and loading and unloading of containers in the yard; Loading system: It consists of a quay crane and a belt conveyor, responsible for container loading operations; Ship unloading system: It consists of a ship unloader and a belt conveyor, responsible for bulk cargo unloading operations; The new dry bulk port multi-scenario simulation targets 6 sub-operation scenarios and their mixed operation scenarios: Train loading operation scenario: filling bulk cargo into containers according to the needs of arriving trains, and then loading containers onto trains; Train unloading operation scene: the operation scene of unloading bulk cargo loaded on the train at the port to the yard; Car loading operation scenario: filling bulk cargo into containers according to the demand of cars arriving at the port, and then loading the containers into cars; Truck unloading operation scene: the operation scene of unloading bulk cargo in the container loaded by the truck at the port to the yard; Ship loading operation scenario: filling bulk cargo into containers according to the needs of arriving ships, and loading containers onto ships; Ship unloading operation scenario: the operation scenario of unloading bulk cargo from a ship at port to the storage yard.

3. The method according to claim 1 or 2, characterized in that: According to the simulation preview requirements of the dry bulk port, combined with historical simulation data, the port production scenarios and simulation data under multiple operation scenarios are collected as training samples, including: Resource allocation data include: port structure information, including terminal layout and division, berth quantity and type, sea freight lines, railway freight lines, and automobile freight lines; equipment information includes: the number, type, and performance parameters of loading and unloading equipment, belt conveyors, and horizontal transportation equipment; personnel allocation information includes: the number, skill level, and working hours of operators, managers, and maintenance personnel; storage capacity information includes: the storage capacity of the yard; The simulation configuration data includes: time parameters include: total simulation running time, time step; input / output data include: freight volume, cargo type, arrival and departure time, loading and unloading time; rule strategies include: scheduling rules, job priority, resource allocation strategy; model parameters include: queue length, storage area and height; The simulation performance data includes: throughput includes: the amount of cargo handled by the port within the preset time; operation time includes: vehicle and ship waiting time, loading and unloading time, transportation time; resource utilization includes: equipment utilization, staffing utilization; congestion includes: vehicle / ship queue length, warehouse inventory.

4. The method according to claim 3, characterized in that The method of using the general knowledge of the large language model to expand the training samples includes: Using the text generation capability of the large language model, a descriptive text is generated based on the defined operation scenarios and simulation data to cover the port operation conditions and simulation data under various operation weather conditions, operation states and operation time periods; According to the historical simulation data format, the descriptive text is converted into structured data suitable for training the simulation model. Through manual review and simulation model testing, it is ensured that the generated samples conform to the physical laws and port business logic. Based on the preliminary simulation results and feedback, the input prompts, generation parameters and data conversion synthesis rules of the large language model are continuously adjusted.

5. The method according to claim 4, characterized in that The training set is used to train the initial large language model, and the verification set is used to verify the initial large language model, including: Divide the training set into multiple subsets according to the set batch size; Randomly extract a batch of data from the training set as the input data and corresponding target value of the current iteration; Input the current batch of data into the initial large language model and calculate the predicted value through forward propagation; Given a target text sequence Y = (y1, y2, ...y T ), calculate the loss function value based on the predicted value and the true target value: Among them, T is the length of the target text sequence, and the probability distribution predicted by the large language model at each step t is y t is the true value of the target sequence at time t; Depend on Calculate the gradient of the loss function with respect to the parameters of the large language model, where is the gradient of the average loss function of the entire sequence with respect to the parameters. For a given target text sequence Y and the probability distribution predicted by the model, θ is the model parameter; The update rule of the Adam optimizer is used to update the large language model parameters, where the first-order moment estimate is updated as Update the second-order moment estimate to The deviation is corrected to Update the parameters to β1 and β2 are hyperparameters, α is the learning rate, t is the current number of iterations, ∈ is a very small positive number, and m t is the first-order exponentially weighted moving average of the gradient, v t is the second-order exponentially weighted moving average of the squared gradient, is the bias-corrected first-order moment, is the bias-corrected second-order moment, θ t+1 To update the parameters; After all batches have been iterated, the model is validated using the validation set. If the validation result fails, the model is returned to the step of dividing the training set into multiple subsets according to the set batch size until the validation result passes.

6. The method according to claim 5, characterized in that The test results based on the test set evaluate the multi-scenario simulation results under the guidance of the large language model, and use the prompt learning mechanism to perform iterative expansion training in combination with multi-scenario data to obtain the trained large language model, including: Use the test set to evaluate the performance of the initial large language model, including model accuracy, stability, and generalization ability; Identify model deficiencies based on evaluation results and guide the model’s behavior in corresponding scenarios by defining new prompt functions or modifying existing prompts; By continuously collecting multi-scenario data, adjusting prompt templates and training strategies, the large language model is trained multiple times.

7. The method according to claim 6, characterized in that The large language model is trained multiple times by continuously collecting multi-scenario data, adjusting prompt templates and training strategies, including: During each iterative training process, new multi-simulation scenario data is continuously collected, pre-processed and annotated; Use the designed prompt template to convert the raw data into the form of prompt input; Input the prompt input and the corresponding label into the pre-trained large language model for training; Based on the difference between the output of the large language model and the true label, the loss function is calculated and the model parameters are updated through back propagation; After each iteration, use the validation set or test set to evaluate the performance of the large language model. Adjust the design of the prompt template based on the evaluation results, and adjust the training strategy based on the performance of the large language model during training; Continue to iterate, constantly collect new data, adjust prompts and training strategies, and iterate training until performance evaluation passes.

8. The method according to claim 7, characterized in that According to the current operation scene of the port, the scene feature corpus is input, and the key semantics of the scene features are extracted through the trained large language model, including: Select text data related to the current port operation scenario, remove invalid information from the text data, and convert unstructured data into a structured format; The large language model uses advanced semantic analysis to identify and distinguish key words, phrases and conceptual entities in the text, and directly maps them to key parameters and operating modes of port operations; Mining the meaning of keywords and phrases in specific scenarios, using contextual information to analyze their functions and relationships, and extracting key semantic information of simulation configurations.

9. The method according to claim 8, characterized in that The use of the trained large language model to perform simulation resource configuration reasoning on the extracted key semantics, thereby obtaining the simulation resource configuration in the current operation scenario, includes: Based on key semantic information, the trained large language model is used to perform simulation resource configuration reasoning. By analyzing the current operation scenario and building the simulation scenario, a reasonable resource configuration plan is inferred, including the quantity allocation of resources such as loading and unloading equipment, transport vehicles, and storage space, operation path planning, and shift scheduling.

10. The method according to claim 9, characterized in that According to the simulation resource configuration provided by the trained large language model, AnyLogic simulation software is used to build a new dry bulk port simulation model in the corresponding scenario, providing simulation preview results for the port, including: Using the simulation resource configuration data provided by the big language model as input, AnyLogic simulation software was used to build an operational system model of a new dry bulk port, including port infrastructure layout, equipment configuration, and operational processes such as ship arrival, cargo loading and unloading, storage, and transportation. Run the simulation model to observe the operation of the port in actual operation, collect simulation preview results of operation time, operation efficiency, equipment utilization, and terminal throughput, so as to make production and operation decisions for the port.

Images